aug_gaussian_noise — Gaussian additive-noise augmentation¶
Group: Augmentation · Binding: n4m.sklearn.GaussianAdditiveNoise · C ABI: n4m_aug_gaussian_noise_*
Description¶
Add IID Gaussian noise to each element of X.
Parameters¶
Name |
Type |
Default |
|---|---|---|
|
|
|
|
|
|
|
|
|
Explanations¶
Bibliographic source¶
Standard data-augmentation perturbation; see the nirs4all augmentation handbook.
Mathematical principle¶
Adds i.i.d. Gaussian noise \(\mathbf{x} + \boldsymbol{\varepsilon}\), \(\varepsilon \sim \mathcal{N}(0,\sigma^2)\), to each element, simulating detector/shot noise to regularise models and enlarge small calibration sets.
Implementation¶
C ABI n4m_aug_gaussian_noise_* in libn4m (create / apply / destroy lifecycle), wrapped by n4m.sklearn.GaussianAdditiveNoise. The same numerical kernel backs every language binding.
Usage¶
from n4m.sklearn import GaussianAdditiveNoise
op = GaussianAdditiveNoise()
X_transformed = op.fit_transform(X)
Benchmarks¶
Adaptive wall-clock per cell measured against full_matrix.csv. Only backends that implement this method are listed; libraries without the method are omitted.
Verdict · ✓ ref / ≈ ref / ~ shape mark a reference-gate pass at strict / relaxed / qualitative tolerance · ✓ bind = pls4all binding agrees with the C++ baseline · ⇄ cross-check = documented by-design selector/RNG/model, noncanonical API/facade convention, or secondary oracle · ✗ divergent · ⚠ error · — not run. The fastest backend per column is marked 🏆.
Reference gate: strict — numeric equivalence (rmse_rel_tol ≤ 1e-12).
| Backend | Parity | 50×250 (ms) | 250×50 (ms) |
|---|---|---|---|
| C++ native · libn4m | |||
pls4all.cpp.blas | ✓ ref | — | 0.10 ms |
pls4all.cpp.blas+omp | ✓ ref | 0.11 ms | 0.11 ms |
pls4all.cpp.omp | ✓ ref | — | 0.11 ms |
pls4all.cpp.ref | ✓ ref | 0.10 ms | 0.15 ms |
| Python · pls4all | |||
pls4all.python | ✓ bind | 0.08 ms🏆 | 0.08 ms🏆 |
pls4all.sklearn | ✓ bind | 0.08 ms | 0.08 ms |
See also: methods index · interactive dashboard